Evolutionary Optimization of a Wavelet Classifier for the Categorization of Beat-to-Beat Variability Signals

  • H. A. Kestler
  • M. Höher
  • G. Palm
Conference paper


The beat-to-beat variation of the QRS and ST-T signal was assessed in healthy volunteers and in patients with malignant tachyarrhythmias using a novel wavelet based classifier designed by an evolutionary algorithm. High-resolution ECGs were recorded in 51 healthy volunteers and in 44 CHD patients with inducible sustained VT. QRS and ST-T variability was analyzed in 250 sinus beats. In each patient a variability signal was created from the standard deviation of corresponding data points of all beats. The complete variability signal was used. Analysis of the whole variability signal with the wavelet classifier results in an improved diagnostic ability of beat-to-beat variability analysis.


Malignant Ventricular Arrhythmia Sinus Beat Electrical Alternans Ventricular Late Potential Wavelet Classifier 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Smith J, Clancy E, Valeri C, Ruskin J, Cohen R. Electrical alternans and cardiac electrical instability. Circulation 1988;77(1):110–121.CrossRefGoogle Scholar
  2. [2]
    Rosenbaum D, Jackson L, Smith J, Garan H, Ruskin J, Cohen R. Electrical Alternans and Vulnerability to Ventricular Arrhythmias. N Engl J Med 1994;330(4):235–41.CrossRefGoogle Scholar
  3. [3]
    Hombach V, Kebbel U, Hopp HW, Winter U, Hirche H. Noninvasive beat-by-beat registration of ventricular late potentials using high resolution electrocardiography. Int J Cardiol 1984;6:167–183.CrossRefGoogle Scholar
  4. [4]
    Hombach V, Kochs M, Höopp HW, et al. Dynamic behavior of ventricular late potentials. In Hombach V, Hilger HH, Kennedy HL (eds.), Electrocardiography and cardiac drug therapy. Dordrecht, Netherlands: Kluwer Academic Publishers, 1989; 218–238.CrossRefGoogle Scholar
  5. [5]
    Sherif NE, Gomes J, Restivo M, Mehra R. Late potentials and arrhythmogenesis. Pacing Clin Electrophysiol 1985;8:440.CrossRefGoogle Scholar
  6. [6]
    Sherif NE, Gough W, Restivo M, Craelius W, Henkin R, Caref E. Electrophysiological basis of ventricular late potentials. Pacing Clin Electrophysiol 1990; 13:2140–7.CrossRefGoogle Scholar
  7. [7]
    Höher M, Axmann J, Eggeling T, Kochs M, Weismüller P, Hombach V. Beat-to-beat variability of ventricular late potentials in the unaveraged high resolution electrocardiogram — effects of antiar-rhythmic drugs. Eur Heart J 1993;14:E:33–39.CrossRefGoogle Scholar
  8. [8]
    Kestler HA, Wohrle J, Höher M. Cardiac vulnerability assessment from electrical microvariability of the high-resolution electrocardiogram. Medical Biological Engineering Computing 2000;38:88–92.CrossRefGoogle Scholar
  9. [9]
    Bäck T. Evolutionary Algorithms in Theory and Practice. New York: Oxford University Press, 1996.MATHGoogle Scholar
  10. [10]
    Ritscher DE, Ernst E, Kammrath HG, Hombach V, Höher M. High-Resolution ECG Analysis Platform with Enhanced Resolution. Computers in Cardiology 1997;24:291–294.Google Scholar
  11. [11]
    van Bemmel J, Musen M (eds.). Handbook of Medical Informatics. Heidelberg/New York: Springer Verlag, 1997.Google Scholar
  12. [12]
    de Boor C. A Practical Guide to Splines. Springer Verlag, 1978.Google Scholar
  13. [13]
    Sammon J. A nonlinear mapping for data structure analysis. IEEE Transactions on Computers May 1969;C-18:401–409.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Wien 2001

Authors and Affiliations

  • H. A. Kestler
    • 1
    • 2
  • M. Höher
    • 2
  • G. Palm
    • 1
  1. 1.Neural Information ProcessingUniversity of UlmGermany
  2. 2.Medicine II — CardiologyUniversity Hospital UlmGermany

Personalised recommendations